Arm backend: Make INT+FP default for vgf-backend #16176
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Make INT+FP default for vgf. With INT+FP, the following issues were solved: - Make sure that pow.Tensor_Scalar is not replaced by pow.Tensor_Tensor during transform_for_annotation. - Make sure that Scalar-ops that also maps to table ops are not replaced by Tensor ops when quantized. - Fix a bug in tosa_supported_operators where nodes with integer outputs were considered ok for partitioning when they shouldn't be. Signed-off-by: Oscar Andersson <oscar.andersson@arm.com> Change-Id: I53c992422b80fd7e93da9d1b07256dccd7115025
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16176
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled Job, 1 Unrelated FailureAs of commit 5a0096e with merge base 152ea3e ( UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
oscarandersson8218
added
partner: arm
zingo
approved these changes
Dec 10, 2025
zingo
approved these changes
Dec 10, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Make INT+FP default for vgf. With INT+FP supported, the following issues were solved:
Test plan
The plan is to move most of the vgf-tests to lower with both INT and FP support. We can then test both the quantized and non-quantized flows.
cc @freddan80 @per @zingo @digantdesai